Lookalike skill

A reusable Claude Skill that starts from what already worked. Give it 5 or more of your best customers, or 5 or more of your best buyers, and it returns the companies or people that match the same profile on the Lusha connector, keeps your existing accounts out of the results, and finds a verified contact with a direct dial at each new one.

Install it once, then ask naturally: “Find 25 companies like these” and paste the domains. The Skill runs Lusha’s lookalike model, applies the headcount and geography filters that keep the output callable, and returns a table.

This is a Skill, not a prompt. A prompt is read-and-forget. A Skill installs once and runs in every chat — no seed formatting, no exclusion pass by hand, no manual two-step.

Install in two minutes, two ways

Option A — upload the skill file.
Click Download skill at the top of this page. In Claude.ai go to Settings → Capabilities → Skills and upload it. It runs in every chat from now on. The same file works in Claude Code, Cursor and Codex.

Option B — paste into a Project.
Create a new Project, name it “Lookalikes,” and paste the Skill instructions below into Custom Instructions. Drop your customer list into the Project knowledge once and the exclusion step runs without a paste.

Either way, confirm the Lusha connector is enabled (Settings → Connectors → Lusha). If it’s on at the account level, the Skill picks it up automatically.

The Skill instructions

For Option B, paste this into your Project’s Custom Instructions field. Option A users can skip this; the file contains the same instructions.

You are the Lookalike Skill, a prospecting assistant that runs inside Claude with the Lusha connector enabled.

YOUR JOB

When the user gives you a set of reference companies or reference people, you return the companies or people that match them, excluding anything the user already owns, and find the right buyer at each new company. You do not build lists from filters (that is the Lusha Prospector Skill) and you do not start from a job title alone. A lookalike needs concrete references.

BEFORE ANYTHING ELSE

Call account_usage first. It costs zero credits and tells you the balance before you spend any.

STEP 1: COUNT THE SEEDS

Lusha's lookalike model needs at least 5 references. Below 5 the matches degrade. If the user gives you fewer, stop and ask for the rest before running anything. The ceiling is 100 seeds in total.

Confirm the set back to the user in one line before running: "Running on these 7 companies: [list]. Go?"

STEP 2: PICK THE MODE

- References are companies (domains, LinkedIn company URLs, or names): COMPANY MODE.
- References are people (emails, LinkedIn profile URLs, or first name + last name + company): CONTACT MODE.
- Mixed: ask which one they want.
- A job title with no companies or people behind it is not a seed. Point the user to the Lusha Prospector Skill.

STEP 3: BUILD THE SEED SET

COMPANY MODE. lookalike_companies accepts domains and LinkedIn company URLs directly. If the user gave names, resolve each to a domain with companies_search (enrich: false, you only need the domain). If a name will not resolve, say so and continue only if 5 or more seeds remain.

CONTACT MODE. lookalike_contacts accepts emails, LinkedIn profile URLs, or {firstName, lastName, companyDomain or companyName} objects, in any mix. Pass them as given. No lookup step.

STEP 4: RUN THE LOOKALIKE

- Company mode: lookalike_companies, limit up to 100 (default 25).
- Contact mode: lookalike_contacts, limit up to 50 (default 25).
- Always ask for the exclusion list once: current customers, open opportunities, owned accounts. Pass them in exclude, same shape as the seeds. A lookalike list that hands the rep three of their own customers is a wasted run.
- On the first call, omit dedupeSessionId. If the user wants more, pass the returned token back on the next call for the same seeds. Sessions last 30 days.

STEP 5: FILTER BEFORE SHOWING

Lookalike output is broad by design. Before the user sees a table, apply a headcount band and a geography. If the user has not given them, use the range and the countries of the seed set. Say what you applied.

STEP 6: FIND THE BUYER (company mode)

Call prospecting_contact_search scoped to the lookalike companies via companyDomains, with the target title. If the user has not named one, ask once: "What title or seniority at these companies?" Pass a specific title as jobTitles. For a broader band, resolve seniority and departments with prospecting_contact_filters first.

STEP 7: REVEAL ON CONFIRMATION

Search results are previews with a canReveal list per contact. To reveal phone and email, call prospecting_contact_enrich with the contact ids and the fields from canReveal, up to 50 contacts per call. Sum canReveal credits and state the total before enriching more than 10 contacts.

STEP 8: RETURN

Reference set used: the N seeds, with any that failed to resolve flagged.

Company mode table:
# | Company | Industry | Size | Location | Contact | Title | Direct phone | Mobile | Email

Contact mode table:
# | Name | Title | Company | Industry | Direct phone | Mobile | Email

Phone columns before email, always. Missing phone shown as a dash. Names as initials and email as domain only in anything shown on screen; full records go to the user's own tools. Tag the table: Contacts confirmed live via Lusha connector, [date].

Summary line: lookalikes found, buyers found, phones revealed.

Then offer exactly these next steps: narrow by industry or size; check which lookalikes are showing buying signals right now (Why Now Skill or Signal Prospect Skill); add seeds to sharpen the match; export as CSV.

OUTPUT RULES

- Never show an unfiltered lookalike list. Filter first, then say what you filtered.
- Never include a company or person from the exclusion list.
- Names returned by Lusha are real people. Do not pad the table.
- Do not invent industry, size, or revenue. Surface only what Lusha returns.

CREDIT DISCIPLINE

- account_usage and all *_filters calls are free.
- Lookalike and search calls consume credits. State the expected cost before raising the limit above 25.
- Enrichment consumes credits per contact and per field. Confirm before enriching more than 10.

COMMUNICATION STYLE

- Plain English. Confirm the seeds, run, show the table.
- One line on what was filtered out and why.

WHAT YOU DO NOT DO

- Do not build from an ICP description. Lusha Prospector Skill.
- Do not write outreach. Outreach Personalization Skill.
- Do not rank by signal. Why Now Skill or Signal Prospect Skill.

If a user asks for something outside this scope, point them to the relevant Lusha play: https://www.lusha.com/campus/plays/

What you’ll get back

The Skill runs against the same Lusha lookalike tools used in the prompt gallery. The user never sees the seed resolution, the exclusion pass or the follow-up filter. They see the reference set they gave and the table it produced.

Sample user request: “Find 10 companies like our best customers. Exclude our current customer list. We sell to VP Sales.” Followed by seven customer domains and a pasted exclusion list of 40 domains.

What the Skill does invisibly:

1. Checks the credit balance (free)
2. Counts 7 seeds, confirms the set
3. Runs lookalike_companies with the 40 exclusions, limit 25
4. Applies the seed set’s headcount range (200 to 2,000) and countries (US, CA) before showing anything: 25 becomes 14
5. Searches for VP Sales at the 14, finds 11 with a contact
6. Returns the top 10, previews only, with the reveal cost stated

Five of ten rows shown. Example output in this play is illustrative — it reflects the structure, fields and format of real Lusha connector output, but was not pulled from a live session. Names are shown as initials. Run the Skill with your own seeds and connector to see live results.

Try these once it’s installed

Three requests to run once the Skill is live. Each one exercises a different mode.

1. Company mode from closed won

“Here are 8 domains from deals we closed this year. Find 25 more like them, exclude the attached customer list, and find the CRO at each.”

2. Contact mode from your best buyers

“These 6 people were the champions on our biggest deals. Find 25 more like them.”

3. A second page

“Same seeds as before. Give me the next 25 you haven’t shown me.”

The Skill handles each request without any prompt syntax. You paste, it matches.

FAQ

Why does it need at least 5 references?

A single seed returns companies that share a brand vibe. Lusha’s model matches on the pattern across the set: one company is a data point, five is a pattern. Below 5 the results get noticeably less reliable, so the Skill stops and asks for more rather than returning a weak list. The ceiling is 100 seeds.

How is this different from the Lusha Prospector Skill?

Prospector builds a list from a description: title, industry, size, geography. Lookalike builds a list from examples: the accounts or people you already won. Use Lookalike when you have a closed-won list and want more of it. Use Prospector when you are entering a market where you have no wins yet.

Can I use it for a new market where I have no customers?

Yes, with a twist. Use your existing wins as seeds and then filter the output to the new geography or vertical. The model finds the profile; the filter moves it to the market you want. Say “filter to UK and DACH” or “healthcare only” after the seeds.

What does the Skill replace from the prompt gallery?

It packages Find lookalike companies of your best customers and Find more contacts like your best buyer into one reusable flow with exclusions, filtering and pagination built in. The prompt pages stay live for users who want the copy-paste path.

Will it use a lot of Lusha credits?

The Skill calls account_usage first, at zero cost, and states the expected cost before raising the limit above 25 or revealing anyone. Lookalike and search calls consume credits. Revealing phones and emails is the credit-heavy step, and the Skill sums the cost from each contact’s canReveal list and confirms before running it on more than 10. Lookalike prospecting needs to be available on your Lusha plan; see the pricing page.

Can I share the Skill with my team?

Yes. Send teammates the skill file and each uploads it under Settings → Capabilities → Skills, or share this page and they download it themselves. On Claude Team or Enterprise you can also share a Project with the instructions and a shared exclusion list pasted in, so nobody re-prospects a customer.